Automatic Identification of Web-Based Risk Markers for Health Events
- Submitting institution
-
University College London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 13990
- Type
- D - Journal article
- DOI
-
10.2196/jmir.4082
- Title of journal
- JOURNAL OF MEDICAL INTERNET RESEARCH
- Article number
- ARTN e29
- First page
- -
- Volume
- 17
- Issue
- 1
- ISSN
- 1438-8871
- Open access status
- Out of scope for open access requirements
- Month of publication
- January
- Year of publication
- 2015
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- 12
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Earlier identification of an individual’s risk of disease can reduce healthcare costs and save lives. This is the first paper to demonstrate that anonymised web search logs can be used to identify individuals at risk, looking at thousands of users and millions of queries. Queries were categorised using an SVM, Wikipedia and DBPedia. The self-controlled case series method was used to discover risks. The paper was awarded the Lloyd’s Science of Risk runner-up prize. Based on our research, subsequent work by others has demonstrated the possibility of earlier detection of cervical, lung, ovarian, and pancreatic cancers.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -